GIS Predictive Model for Producing Hydrothermal Gold Potential Map Using Weights of Evidence Approach in Gengma Region, Sanjiang District, China

Gengma region, Sanjiang district is known to have some large-scale gold deposits. GIS predictive model for hydrothermal gold potential was carried out in this region using weights of evidence modeling technique. Datasets used include large-scale hydrothermal gold deposit records, geological, geophysical and remote sensing imagery. Based on the geological and mineral characteristics of areas with known gold occurrences in Sanjiang, several geological features were thought to be indicative of areas with potential for the occurrence of hydrothermal gold deposits. Indicative features were extracted from geoexploration datasets for use as input in the predictive model. The features include host rock lithology, geologic structures, wallrock alteration and associated (volcanic-plutonic) igneous rocks. To determine which of the indicative geological features are important spatial predictors of area with potential for gold deposits, spatial analysis was done through the modeling method. The input maps were buffered and the optimum distance of spatial association for each geological feature was determined by calculating the contrast and studentized contrast. Five feature maps were converted to binary predictor patterns and used as evidential layers for predictive modeling. The binary patterns were integrated in two combinations, each of which consists of four patterns in order to avoid over prediction due to the effect of duplicate features in the two structural evidences. The two produced potential maps define almost similar favorable zones. Areas of intersections between these zones in the two potential maps placed the highest predictive favorable zones in the region.

Omnibus Weights of Evidence Method Implemented in GeoDAS GIS for Information Extraction and Integration

Weights of evidence （WofE） is an artificial intelligent method for integration of information from diverse sources for predictive purpose in supporting decision making. This method has been commonly used to predict point events by integrating point training layer and binary or ternary evidential layers （multiclass evidence less commonly used）. Omnibus weights of evidence integrates fuzzy training layer and diverse evidential layers. This method provides new features in comparison with the ordinary Wore method. This new method has been implemented in a geographic information system-geophysical data analysis system and the method includes the following contents： （1） dual fuzzy weights of evidence （DFWofE）, in which training layer and evidential layers can be treated as fuzzy sets. DFWofE can be used to predict not only point events but also area or line events. In this model a fuzzy training layer can be defined based on point, line, and areas using fuzzy membership function; and （2） degree-of-exploration model for WorE is implemented through building a degree of exploration map. This method can be used to assess possible spatial correlations between the degree of exploration and potential evidential layers. Importantly, it would also make it possible to estimate undiscovered resources, if the degree of exploration map is combined with other models that predict where such resources are most likely to occur. These methods and relevant systems were vafidated using a case study of mineral potential prediction in Gejiu （个旧） mineral district, Yunnan （ 云南）, China.

A Combined Weight of Evidence and Logistic Regression Method for Susceptibility Mapping of Earthquake-induced Landslides: A Case Study of the April 20, 2013 Lushan Earthquake, China

The M_s 7.0 Lushan earthquake triggered a huge number of landslides. Landslide susceptibility mapping is of great importance. Weight of Evidence（Wo E） and Logistic Regression（LR） methods have been widely used for LSM（Landslide Susceptibility Mapping）. However, limitations still exist. Wo E is capable of assessing the influence of different classes of each factor, but neglects the correlation between factors. LR is able to analyze the relationship among the factors while it is not capable of evaluating the influence of different classes. This paper proposes a combined method of LR and Wo E for LSM, taking advantage of their individual merits and overcoming their limitations. An inventory of 1289 landslides was used： 70% were random-selected for training and the remaining for validation. 11 landslide condition factors were employed in the model and the result was validated using Receiver Operating Characteristic（ROC） curve. The results showed that the LRWo E model had a better accuracy than the LR model, producing an area below the curve with values of 0.802 success and 0.791 predictive, higher than that of the LR model（0.715 success and 0.722 predictive）. It is therefore concluded that the combined method of Wo E and LR can provide a promising level of accuracy for earthquake-induced landslide susceptibility mapping.

Glacial debris flow susceptibility mapping based on combined models in the Parlung Tsangpo Basin,China

Machine learning(ML)-based prediction models for mapping hazard(e.g.,landslide and debris flow)susceptibility have been widely developed in recent research.However,in some specific areas,ML models have limited application because of the uncertainties in identifying negative samples.The Parlung Tsangpo Basin exemplifies a region prone to recurrent glacial debris flows(GDFs)and is characterized by a prominent landform featuring deep gullies.Considering the limitations of the ML model,we developed and compared two combined statistical models(FA-WE and FA-IC)based on factor analysis(FA),weight of evidence(WE),and the information content(IC)method.The final GDF susceptibility maps were generated by selecting 8 most important static factors and considering the influence of precipitation.The results show that the FA-IC model has the best performance.The areas with a very high susceptibility to GDFs are primarily located in the narrow valley section upstream,on both sides of the valley in the middle and downstream of the Parlung Tsangpo River,and in the narrow valley section of each tributary.These areas encompass 86 gullies and are characterized as"narrow and steep".

Predicting of dust storm source by combining remote sensing, statistic-based predictive models and game theory in the Sistan watershed, southwestern Asia

Dust storms in arid and desert areas affect radiation budget,air quality,visibility,enzymatic activities,agricultural products and human health.Due to increased drought and land use changes in recent years,the frequency of dust storms occurrence in Iran has been increased.This study aims to identify dust source areas in the Sistan watershed(Iran-Afghanistan borders)-an important regional source for dust storms in southwestern Asia,using remote sensing(RS)and bivariate statistical models.Furthermore,this study determines the relative importance of factors controlling dust emissions using frequency ratio(FR)and weights of evidence(WOE)models and interpretability of predictive models using game theory.For this purpose,we identified 211 dust sources in the study area and generated a dust source distribution map-inventory map-by dust source potential index based on RS data.In addition,spatial maps of topographic factors affecting dust source areas including soil,lithology,slope,Normalized difference vegetation index(NDVI),geomorphology and land use were prepared.The performance of two models(WOE and FR)was evaluated using the area under curve(AUC)of the receiver operating characteristic curve.The results showed that soil,geomorphology and slope exhibited the greatest influence in the dust source areas.The 55.3%(according to FR)and 62.6%(according to WOE)of the total area were classified as high and very high potential dust sources,while both models displayed acceptable accuracy with subsurface levels of 0.704 for FR and 0.751 for WOE,although they predict different fractions of dust potential classes.Based on Shapley additive explanations(SHAP),three factors,i.e.,soil,slope and NDVI have the highest impact on the model's output.Overall,combination of statistic-based predictive models(or data mining models),RS and game theory techniques can provide accurate maps of dust source areas in arid and semi-arid regions,which can be helpful for mitigation of negative effects of dust storms.

Quantifying the influence of magmatism and tectonism on ultraslow-spreading-ridge hydrothermal activity:Evidence from the Southwest Indian Ridge

Hydrothermal activity in mid-ocean ridges(MORs)is an important intermediary for the mass and heat exchange between the ocean and lithosphere.The development of hydrothermal activity on MORs is primarily controlled by coupled magmatic and tectonic activities.In ultraslow-spreading ridges,deepdipping low-angle normal faults with large offsets,typically detachment faults in the inside corners of ridge offsets,favor the formation of tectonic-related hydrothermal activities,whereas volcanic-related hydrothermal fields are typically developed in neovolcanic zones in this category of the ridge system.However,whether tectonic or magmatic activity is dominant and to what extent they control the formation of hydrothermal activities on ultraslow-spreading ridges remain unclear.Segments in the west and east of the Gallieni transform fault(TF)located in the ultraslow-spreading Southwest Indian Ridge(SWIR),namely,western area(WA)and eastern area(EA),exhibit distinct magma-supply conditions that provide favorable conditions for examining the influence of magmatic and tectonic activities.We generated prediction models for these areas using the spatial analysis of the water depth,minor faults,large faults,ridge axis,nontransform discontinuity(NTD)inside corners,TF inside corners,Bouguer gravity anomaly,magnetic anomalies,and seismic activities.By employing the weights of evidence method,we reported that the formation of seafloor hydrothermal systems in SWIR was primarily correlated to the NTD inside corner,ridge axis,and minor fault(i.e.,contrast values(C)of 4.186,3.727,and 3.482 in WA and 4.278,3.769,and 3.135 in EA).Furthermore,EA was significantly affected by the TF inside corner(C=3.501),whereas WA was influenced by large faults(C=4.062).Our results demonstrated that tectonism was the primary controlling factor in the development of hydrothermal activities in the study area,and the contribution of magmatism was secondary,even in WA,which has a relatively robust magma supply.We delimited prominent prospecting areas at each side based on posterior probability.Our results provided insights into the formation mechanisms of hydrothermal activities and support prospecting in MORs.

The quest for conditional independence in prospectivity modeling： weights-of-evidence, boost weights-of-evidence, and logistic regression

The objective of prospectivity modeling is prediction of the conditional probability of the presence T = 1 or absence T = 0 of a target T given favorable or prohibitive predictors B, or construction of a two classes {0,1} classification of T. A special case of logistic regression called weights-of-evidence （WofE） is geolo- gists＇ favorite method of prospectivity modeling due to its apparent simplicity. However, the numerical simplicity is deceiving as it is implied by the severe mathematical modeling assumption of joint conditional independence of all predictors given the target. General weights of evidence are explicitly introduced which are as simple to estimate as conventional weights, i.e., by counting, but do not require conditional independence. Complementary to the regres- sion view is the classification view on prospectivity modeling. Boosting is the construction of a strong classifier from a set of weak classifiers. From the regression point of view it is closely related to logistic regression. Boost weights-of-evidence （BoostWofE） was introduced into prospectivity modeling to counterbalance violations of the assumption of conditional independence even though relaxation of modeling assumptions with respect to weak classifiers was not the （initial） purpose of boosting. In the original publication of BoostWofE a fabricated dataset was used to ＂validate＂ this approach. Using the same fabricated dataset it is shown that BoostWofE cannot generally compensate lacking condi- tional independence whatever the consecutively proces- sing order of predictors. Thus the alleged features of BoostWofE are disproved by way of counterexamples, while theoretical findings are confirmed that logistic regression including interaction terms can exactly com- pensate violations of joint conditional independence if the predictors are indicators.

Landslide Hazard Mapping Using GIS and Weight of Evidence Model in Qingshui River Watershed of 2008 Wenchuan Earthquake Struck Region

Tens of thousands of landslides were triggered by May 12, 2008 earthquake over a broad area. The main purpose of this article is to apply and verify earthquake-triggered landslide hazard analysis techniques by using weight of evidence modeling in Qingshui （清水） River watershed, Deyang （德阳） City, Sichuan （四川） Province, China. Two thousand three hundred and twenty-one landslides were interpreted in the study area from aerial photographs and multi-source remote sensing imageries post-earthquake, verified by field surveys. The landslide inventory in the study area was established. A spatial database, including landslides and associated controlling parameters that may have influence on the occurrence of landslides, was constructed from topographic maps, geological maps, and enhanced thematic mapper （ETM＋） remote sensing imageries. The factors that influence landslide occurrence,such as slope angle, aspect, curvature, elevation, flow accumulation, distance from drainages, and distance from roads were calculated from the topographic maps. Lithology, distance from seismogenic fault, distance from all faults, and distance from stratigraphic boundaries were derived from the geological maps. Normalized difference vegetation index （NDV1） was extracted from ETM＋ images. Seismic intensity zoning was collected from Wenchuan （汶川） Ms8.0 Earthquake Intensity Distribution Map published by the China Earthquake Administration.Landslide hazard indices were calculated using the weight of evidence model, and landslide hazard maps were calculated from using different controlling parameters cases. The hazard map was compared with known landslide locations and verified. The success accuracy percentage of using all 13 controlling parameters was 71.82%. The resulting landslide hazard map showed five classes of landslide hazard, i.e., very high, high, moderate, low, and very low. The validation results showed satisfactory agreement between the hazard map and the existing landslides distribution data. The landslide hazard map can be used to identify and delineate unstable hazard-prone areas. It can also help planners to choose favorable locations for development schemes, such as infrastructural, buildings, road constructions, and environmental protection.

Research on Personal Credit Evaluation Based on Mobile Telecommunications Data

With the rapid development of big data technology, the personal credit evaluation industry has entered a new stage. Among them, the evaluation of personal credit based on mobile telecommunications data is one of the hotspots of current research. However, due to the complexity and diversity of personal credit evaluation variables, in order to reduce the complexity of the model and improve the prediction accuracy of the model, we need to reduce the dimension of the input variables. According to the data provided by a mobile telecommunications operator, this paper divides the data into a training sets and verification sets. We perform correlation analysis on each indicator of the data in the training set, and calculate the corresponding IV value based on the WOE value of the selected index, then binning data with SPSS Modeler. The selected variables were modeled using a logistic regression algorithm. In order to make the regression results more practical, we extract the scoring rules according to the results of logistic regression, convert them into the form of score cards, and finally verify the validity of the model.

A Predictive GIS Model for Potential Mapping of Copper, Lead, and Zinc in Langping Area, China

Mineral resource potential mapping is a complex analytical process,which requires the consideration and the inte-gration of a number of spatial evidences like geological,geomorphological,and wall rock alteration.The aim of this paper is to establish mineral exploration model for copper,lead,and zinc in Lanping basin area using the capability of analytical tools of Geographic Information System(GIS) and remote sensing data to generate maps showing favorable mineralized area.The geo-exploration dataset used for the research includes copper,lead,and zinc deposits,geological maps,topographic maps,structural maps,and ETM+ imagery.Geological features indicative of potential copper,lead,and zinc were extracted from the datasets input in the predictive model.The method of weights of evidence modeling is a probability-based technique for generating mineral potential maps using the spatial distribution of indicative features with respect to the known mineral occur-rences.The method of weights of evidence probabilistic modeling provides a quantitative method for delineating areas with potential of copper,lead,and zinc mineral deposits in the Lanping Basin area.weights(W+,W-) and contrast(C=(W+) -(W-) ) calculations guide the data-driven modeling.The four most important spatial features for exploration guide for copper,lead,and zinc mineralization hosted in the Lanping Basin area are alteration zones,faults,host rocks,and lineaments.The host rocks and deep faults have the strongest spatial association with the known copper,lead,and zinc deposits.The hydrothermal alteration zones have the moderate spatial association with the copper,lead,and zinc deposits.The predicted high-favorability zones do not show the strong affinity with lineaments.The distribution of 22(copper,lead,and zinc) occur-rences in the Lanping Basin was examined in terms of spatial association with various geological phenomena.The analysis of these relationships using GIS and weights of evidence modeling has predicted areas of high and moderate mineral potential,where a little or no mining activities exist.

Resource prediction and assessment based on 3D/4D big data modeling and deep integration in key ore districts of North China

The North China district has been subjected to significant research with regard to the ore-forming dynamics,processes,and quantitative forecasting of gold deposits;it accounts for the highest number of gold reserves and annual products in China.Based on the top-level design of geoscience theory and the method adopted by the National Key R&D Project(deep process and metallogenic mechanism of North China Craton(NCC)metallogenic system),this paper systematically collects and constructs the geoscience data(district,camp,and deposit scales)in four key gold districts of North China(Jiaojia-Sanshandao,Southern Zhaoping,Wulong,and Qingchengzi).The settings associated with the geological dynamics of gold deposits were quantitatively and synthetically analyzed,namely:NCC destruction,metallogenic events,genetic models,and exploration models.Three-dimensional(3D)and four-dimensional(4D)geological modeling was performed using the big data on the districts,while the district-scale 3D exploration criteria were integrated to construct a quantitative exploration model.Among them,FLAC3D modelling and the Geo Cube software(version 3.0)were used to implement the numerical simulation of the 3D geological models and the constraints of the fluid saturation parameters of the Jiaojia fault to reconstruct the 4D fault structure models of the Jiaojia fault(with a depth of 5000 m).Using Geo Cube3.0,multiple integration modules(general weights of evidence(Wof E),Boost Wof E,Fuzzy Wof E,Logistic Regression,Information Entropy,and Random Forest)and exploration criteria were integrated,while the C-V fractal classification of A,B and C targets in four districts was carried out.The research results are summarized in the following four areas:(1)Four gold districts in the study area have more than three targets(the depth is 3000 m),and the class A,B and C targets exhibit a good spatial correlation with gold bodies that are controlled by mining engineering at depths greater than 1000 m.(2)The Boost Wof E method was used to identify the target optimization in 3D spaces(at depths of 3000–5000 m)of the Jiaojia-Sanshandao,Southern Zhaoping,and Wulong districts.(3)The general Wof E method is based on the Bayesian theory in 3D space and provides robust integration and target optimization that are suitable for the Jiaojia-Sanshandao and Southern Zhaoping districts in the Jiaodong area;it can also be applied to the Wulong district in the Liaodong area using a quantitative genetic model and an exploration model.Random forest is a multi-objective integration and target optimization method for 3D spaces,and it is suitable for the complex exploration model in the Qingchengzi district of the Liaodong area.The genetic model and exploration criteria associated with the exploration model of the Qingchengzi district were constrained by the common characteristics of the gold fault structure,magmatic rock emplacement in North China,and the strata fold and interlayer detachment structure.(4)Based on the gold reserves and the 3D block unit model of the Sanshandao gold deposit in the Jiaojia-Sanshandao district,the gold contents of the 3D block units in class A and B targets of the ore concentration were estimated to be 65.5%and 25.1%,respectively.The total Au resources of the optimized targets below a depth of 3000 m were 3908 t(including 1700 t reserves),and the total Au resources of the targets at depths from 3000 to 5000 m were 936 t.The study shows that the deep gold deposits in the four gold districts of North China exhibit a strong"transport-deposition"spatial correlation with potential targets.These"transport-deposition"spatial models represent the tectonic-magmatic-hydrothermal activities of the metallogenic system associated with the NCC destruction events and indicate the Au enrichment zones.

Quantitative prediction and evaluation of geothermal resource areas in the southwest section of the Mid-Spine Belt of Beautiful China

The geothermal resources in the southwest section of the Mid-Spine Belt of Beautiful China are abundant,but the quantitative prediction and evaluation of geothermal resources are very difficult. Based on geographic information system (GIS) and remote sensing (RS) platforms,six impact factors,namely land surface temperature,fault density,Gutenberg–Liszt B value,formation combination entropy,distance to river and aeromagnetic anomaly were selected. Through the establishment of the certainty factor model (CF),weights of the information entropy certainty factor model (ICF) and weights of the evidence certainty factor model (ECF),the geothermal potential in the study area were predicted quantitatively. Based on the ECF results,the six main geothermal resource areas were delineated. The results show that (1) ECF had high prediction accuracy (success index is 0.00405%,area ratio is 0.867);(2) The geothermal resource areas obtained were Ganzi–Ya’an–Liangshan,Panzhihua–Liangshan,Dali–Chuxiong,Nujiang–Baoshan,Diqing–Dali,and Lijiang–Diqing. The results provide a basis for the effective development and utilization of geothermal resources in the southwest section of the mid-ridge belt.